Corrective RAG (CRAG)
CRAG adds a self-correcting loop around retrieval so a RAG system can detect and repair bad retrievals instead of feeding them straight into generation.
Ask this paper
Retrieval evaluator: A lightweight evaluator scores the quality of retrieved documents for a given query and classifies the retrieval state as Correct, Incorrect, or Ambiguous.
Action policy: Correct retrievals are refined via decompose-then-recompose filtering; Incorrect retrievals trigger web search to find better evidence; Ambiguous ones combine both signals.
Plug-and-play: CRAG is designed to sit on top of any existing RAG pipeline without retraining the generator, making it easy to adopt incrementally.
Benchmarks: Improves generation quality across short- and long-form QA benchmarks compared to vanilla RAG and Self-RAG baselines, especially when the underlying retriever is noisy.